A deep convolutional neural network model to classify heartbeats

The electrocardiogram (ECG) is a standard test used to monitor the activity of the heart. Many cardiac abnormalities will be manifested in the ECG including arrhythmia which is a general term that refers to an abnormal heart rhythm. The basis of arrhythmia diagnosis is the identification of normal v...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computers in biology and medicine Ročník 89; s. 389 - 396
Hlavní autori: Acharya, U. Rajendra, Oh, Shu Lih, Hagiwara, Yuki, Tan, Jen Hong, Adam, Muhammad, Gertych, Arkadiusz, Tan, Ru San
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Elsevier Ltd 01.10.2017
Elsevier Limited
Predmet:
Abnormalities
Arrhythmia
Arrhythmias, Cardiac - diagnosis
Arrhythmias, Cardiac - physiopathology
Artificial intelligence
Artificial neural networks
Automation
Cardiac arrhythmia
Cardiology
Cardiovascular disease
Cardiovascular diseases
Classification
Convolutional neural network
Databases, Factual
Deep learning
Diagnostic systems
Echocardiography
EKG
Electrocardiogram signals
Electrocardiography
Female
Heart
Heart diseases
Heart Rate
Heartbeat
Humans
Male
Models, Cardiovascular
Morphology
Myocardial Contraction
Neural networks
Neural Networks (Computer)
Noise
PhysioBank MIT-BIH arrhythmia database
Principal components analysis
Signal Processing, Computer-Assisted
Ventricle
Deep learning
Electrocardiogram signals
Arrhythmia
PhysioBank MIT-BIH arrhythmia database
Convolutional neural network
Heartbeat
Cardiovascular diseases
ISSN:0010-4825, 1879-0534, 1879-0534
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The electrocardiogram (ECG) is a standard test used to monitor the activity of the heart. Many cardiac abnormalities will be manifested in the ECG including arrhythmia which is a general term that refers to an abnormal heart rhythm. The basis of arrhythmia diagnosis is the identification of normal versus abnormal individual heart beats, and their correct classification into different diagnoses, based on ECG morphology. Heartbeats can be sub-divided into five categories namely non-ectopic, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats. It is challenging and time-consuming to distinguish these heartbeats on ECG as these signals are typically corrupted by noise. We developed a 9-layer deep convolutional neural network (CNN) to automatically identify 5 different categories of heartbeats in ECG signals. Our experiment was conducted in original and noise attenuated sets of ECG signals derived from a publicly available database. This set was artificially augmented to even out the number of instances the 5 classes of heartbeats and filtered to remove high-frequency noise. The CNN was trained using the augmented data and achieved an accuracy of 94.03% and 93.47% in the diagnostic classification of heartbeats in original and noise free ECGs, respectively. When the CNN was trained with highly imbalanced data (original dataset), the accuracy of the CNN reduced to 89.07%% and 89.3% in noisy and noise-free ECGs. When properly trained, the proposed CNN model can serve as a tool for screening of ECG to quickly identify different types and frequency of arrhythmic heartbeats. [Display omitted] •Convolutional neural network (CNN) is used to classify 5 ECG classes.•9-layer deep CNN is implemented.•Generated synthetic data to overcome imbalance problem.•Accuracy of 94.03% and 93.47% with and without noise removal respectively.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2017.08.022